Diffusion models have revolutionized text-to-image generation with its
e...
AI tasks encompass a wide range of domains and fields. While numerous AI...
Diffusion models have emerged as a powerful tool for point cloud generat...
Retriever-reader models achieve competitive performance across many diff...
Deep generative models have shown success in generating 3D shapes with
d...
We present rectified flow, a surprisingly simple approach to learning
(n...
AI-based molecule generation provides a promising approach to a large ar...
Diffusion-based generative models have achieved promising results recent...
We propose discrete Langevin proposal (DLP), a simple and scalable
gradi...
Active learning, which effectively collects informative unlabeled data f...
Generating images from natural language instructions is an intriguing ye...
The goal of multi-task learning is to enable more efficient learning tha...
Self-attention, as the key block of transformers, is a powerful mechanis...
Learning monotonic models with respect to a subset of the inputs is a
de...
We consider the post-training quantization problem, which discretizes th...